Admin: misc improvements on admin server and workers. EC now works. (#7055)
* initial design * added simulation as tests * reorganized the codebase to move the simulation framework and tests into their own dedicated package * integration test. ec worker task * remove "enhanced" reference * start master, volume servers, filer Current Status ✅ Master: Healthy and running (port 9333) ✅ Filer: Healthy and running (port 8888) ✅ Volume Servers: All 6 servers running (ports 8080-8085) 🔄 Admin/Workers: Will start when dependencies are ready * generate write load * tasks are assigned * admin start wtih grpc port. worker has its own working directory * Update .gitignore * working worker and admin. Task detection is not working yet. * compiles, detection uses volumeSizeLimitMB from master * compiles * worker retries connecting to admin * build and restart * rendering pending tasks * skip task ID column * sticky worker id * test canScheduleTaskNow * worker reconnect to admin * clean up logs * worker register itself first * worker can run ec work and report status but: 1. one volume should not be repeatedly worked on. 2. ec shards needs to be distributed and source data should be deleted. * move ec task logic * listing ec shards * local copy, ec. Need to distribute. * ec is mostly working now * distribution of ec shards needs improvement * need configuration to enable ec * show ec volumes * interval field UI component * rename * integration test with vauuming * garbage percentage threshold * fix warning * display ec shard sizes * fix ec volumes list * Update ui.go * show default values * ensure correct default value * MaintenanceConfig use ConfigField * use schema defined defaults * config * reduce duplication * refactor to use BaseUIProvider * each task register its schema * checkECEncodingCandidate use ecDetector * use vacuumDetector * use volumeSizeLimitMB * remove remove * remove unused * refactor * use new framework * remove v2 reference * refactor * left menu can scroll now * The maintenance manager was not being initialized when no data directory was configured for persistent storage. * saving config * Update task_config_schema_templ.go * enable/disable tasks * protobuf encoded task configurations * fix system settings * use ui component * remove logs * interface{} Reduction * reduce interface{} * reduce interface{} * avoid from/to map * reduce interface{} * refactor * keep it DRY * added logging * debug messages * debug level * debug * show the log caller line * use configured task policy * log level * handle admin heartbeat response * Update worker.go * fix EC rack and dc count * Report task status to admin server * fix task logging, simplify interface checking, use erasure_coding constants * factor in empty volume server during task planning * volume.list adds disk id * track disk id also * fix locking scheduled and manual scanning * add active topology * simplify task detector * ec task completed, but shards are not showing up * implement ec in ec_typed.go * adjust log level * dedup * implementing ec copying shards and only ecx files * use disk id when distributing ec shards 🎯 Planning: ActiveTopology creates DestinationPlan with specific TargetDisk 📦 Task Creation: maintenance_integration.go creates ECDestination with DiskId 🚀 Task Execution: EC task passes DiskId in VolumeEcShardsCopyRequest 💾 Volume Server: Receives disk_id and stores shards on specific disk (vs.store.Locations[req.DiskId]) 📂 File System: EC shards and metadata land in the exact disk directory planned * Delete original volume from all locations * clean up existing shard locations * local encoding and distributing * Update docker/admin_integration/EC-TESTING-README.md Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * check volume id range * simplify * fix tests * fix types * clean up logs and tests --------- Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Chris Lu
@@ -12,6 +12,7 @@ import (
|
||||
func (s *AdminServer) GetClusterCollections() (*ClusterCollectionsData, error) {
|
||||
var collections []CollectionInfo
|
||||
var totalVolumes int
|
||||
var totalEcVolumes int
|
||||
var totalFiles int64
|
||||
var totalSize int64
|
||||
collectionMap := make(map[string]*CollectionInfo)
|
||||
@@ -28,6 +29,7 @@ func (s *AdminServer) GetClusterCollections() (*ClusterCollectionsData, error) {
|
||||
for _, rack := range dc.RackInfos {
|
||||
for _, node := range rack.DataNodeInfos {
|
||||
for _, diskInfo := range node.DiskInfos {
|
||||
// Process regular volumes
|
||||
for _, volInfo := range diskInfo.VolumeInfos {
|
||||
// Extract collection name from volume info
|
||||
collectionName := volInfo.Collection
|
||||
@@ -69,12 +71,13 @@ func (s *AdminServer) GetClusterCollections() (*ClusterCollectionsData, error) {
|
||||
totalSize += int64(volInfo.Size)
|
||||
} else {
|
||||
newCollection := CollectionInfo{
|
||||
Name: collectionName,
|
||||
DataCenter: dc.Id,
|
||||
VolumeCount: 1,
|
||||
FileCount: int64(volInfo.FileCount),
|
||||
TotalSize: int64(volInfo.Size),
|
||||
DiskTypes: []string{diskType},
|
||||
Name: collectionName,
|
||||
DataCenter: dc.Id,
|
||||
VolumeCount: 1,
|
||||
EcVolumeCount: 0,
|
||||
FileCount: int64(volInfo.FileCount),
|
||||
TotalSize: int64(volInfo.Size),
|
||||
DiskTypes: []string{diskType},
|
||||
}
|
||||
collectionMap[collectionName] = &newCollection
|
||||
totalVolumes++
|
||||
@@ -82,6 +85,63 @@ func (s *AdminServer) GetClusterCollections() (*ClusterCollectionsData, error) {
|
||||
totalSize += int64(volInfo.Size)
|
||||
}
|
||||
}
|
||||
|
||||
// Process EC volumes
|
||||
ecVolumeMap := make(map[uint32]bool) // Track unique EC volumes to avoid double counting
|
||||
for _, ecShardInfo := range diskInfo.EcShardInfos {
|
||||
// Extract collection name from EC shard info
|
||||
collectionName := ecShardInfo.Collection
|
||||
if collectionName == "" {
|
||||
collectionName = "default" // Default collection for EC volumes without explicit collection
|
||||
}
|
||||
|
||||
// Only count each EC volume once (not per shard)
|
||||
if !ecVolumeMap[ecShardInfo.Id] {
|
||||
ecVolumeMap[ecShardInfo.Id] = true
|
||||
|
||||
// Get disk type from disk info, default to hdd if empty
|
||||
diskType := diskInfo.Type
|
||||
if diskType == "" {
|
||||
diskType = "hdd"
|
||||
}
|
||||
|
||||
// Get or create collection info
|
||||
if collection, exists := collectionMap[collectionName]; exists {
|
||||
collection.EcVolumeCount++
|
||||
|
||||
// Update data center if this collection spans multiple DCs
|
||||
if collection.DataCenter != dc.Id && collection.DataCenter != "multi" {
|
||||
collection.DataCenter = "multi"
|
||||
}
|
||||
|
||||
// Add disk type if not already present
|
||||
diskTypeExists := false
|
||||
for _, existingDiskType := range collection.DiskTypes {
|
||||
if existingDiskType == diskType {
|
||||
diskTypeExists = true
|
||||
break
|
||||
}
|
||||
}
|
||||
if !diskTypeExists {
|
||||
collection.DiskTypes = append(collection.DiskTypes, diskType)
|
||||
}
|
||||
|
||||
totalEcVolumes++
|
||||
} else {
|
||||
newCollection := CollectionInfo{
|
||||
Name: collectionName,
|
||||
DataCenter: dc.Id,
|
||||
VolumeCount: 0,
|
||||
EcVolumeCount: 1,
|
||||
FileCount: 0,
|
||||
TotalSize: 0,
|
||||
DiskTypes: []string{diskType},
|
||||
}
|
||||
collectionMap[collectionName] = &newCollection
|
||||
totalEcVolumes++
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -112,6 +172,7 @@ func (s *AdminServer) GetClusterCollections() (*ClusterCollectionsData, error) {
|
||||
Collections: []CollectionInfo{},
|
||||
TotalCollections: 0,
|
||||
TotalVolumes: 0,
|
||||
TotalEcVolumes: 0,
|
||||
TotalFiles: 0,
|
||||
TotalSize: 0,
|
||||
LastUpdated: time.Now(),
|
||||
@@ -122,8 +183,203 @@ func (s *AdminServer) GetClusterCollections() (*ClusterCollectionsData, error) {
|
||||
Collections: collections,
|
||||
TotalCollections: len(collections),
|
||||
TotalVolumes: totalVolumes,
|
||||
TotalEcVolumes: totalEcVolumes,
|
||||
TotalFiles: totalFiles,
|
||||
TotalSize: totalSize,
|
||||
LastUpdated: time.Now(),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// GetCollectionDetails retrieves detailed information for a specific collection including volumes and EC volumes
|
||||
func (s *AdminServer) GetCollectionDetails(collectionName string, page int, pageSize int, sortBy string, sortOrder string) (*CollectionDetailsData, error) {
|
||||
// Set defaults
|
||||
if page < 1 {
|
||||
page = 1
|
||||
}
|
||||
if pageSize < 1 || pageSize > 1000 {
|
||||
pageSize = 25
|
||||
}
|
||||
if sortBy == "" {
|
||||
sortBy = "volume_id"
|
||||
}
|
||||
if sortOrder == "" {
|
||||
sortOrder = "asc"
|
||||
}
|
||||
|
||||
var regularVolumes []VolumeWithTopology
|
||||
var ecVolumes []EcVolumeWithShards
|
||||
var totalFiles int64
|
||||
var totalSize int64
|
||||
dataCenters := make(map[string]bool)
|
||||
diskTypes := make(map[string]bool)
|
||||
|
||||
// Get regular volumes for this collection
|
||||
regularVolumeData, err := s.GetClusterVolumes(1, 10000, "volume_id", "asc", collectionName) // Get all volumes
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
regularVolumes = regularVolumeData.Volumes
|
||||
totalSize = regularVolumeData.TotalSize
|
||||
|
||||
// Calculate total files from regular volumes
|
||||
for _, vol := range regularVolumes {
|
||||
totalFiles += int64(vol.FileCount)
|
||||
}
|
||||
|
||||
// Collect data centers and disk types from regular volumes
|
||||
for _, vol := range regularVolumes {
|
||||
dataCenters[vol.DataCenter] = true
|
||||
diskTypes[vol.DiskType] = true
|
||||
}
|
||||
|
||||
// Get EC volumes for this collection
|
||||
ecVolumeData, err := s.GetClusterEcVolumes(1, 10000, "volume_id", "asc", collectionName) // Get all EC volumes
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
ecVolumes = ecVolumeData.EcVolumes
|
||||
|
||||
// Collect data centers from EC volumes
|
||||
for _, ecVol := range ecVolumes {
|
||||
for _, dc := range ecVol.DataCenters {
|
||||
dataCenters[dc] = true
|
||||
}
|
||||
}
|
||||
|
||||
// Combine all volumes for sorting and pagination
|
||||
type VolumeForSorting struct {
|
||||
Type string // "regular" or "ec"
|
||||
RegularVolume *VolumeWithTopology
|
||||
EcVolume *EcVolumeWithShards
|
||||
}
|
||||
|
||||
var allVolumes []VolumeForSorting
|
||||
for i := range regularVolumes {
|
||||
allVolumes = append(allVolumes, VolumeForSorting{
|
||||
Type: "regular",
|
||||
RegularVolume: ®ularVolumes[i],
|
||||
})
|
||||
}
|
||||
for i := range ecVolumes {
|
||||
allVolumes = append(allVolumes, VolumeForSorting{
|
||||
Type: "ec",
|
||||
EcVolume: &ecVolumes[i],
|
||||
})
|
||||
}
|
||||
|
||||
// Sort all volumes
|
||||
sort.Slice(allVolumes, func(i, j int) bool {
|
||||
var less bool
|
||||
switch sortBy {
|
||||
case "volume_id":
|
||||
var idI, idJ uint32
|
||||
if allVolumes[i].Type == "regular" {
|
||||
idI = allVolumes[i].RegularVolume.Id
|
||||
} else {
|
||||
idI = allVolumes[i].EcVolume.VolumeID
|
||||
}
|
||||
if allVolumes[j].Type == "regular" {
|
||||
idJ = allVolumes[j].RegularVolume.Id
|
||||
} else {
|
||||
idJ = allVolumes[j].EcVolume.VolumeID
|
||||
}
|
||||
less = idI < idJ
|
||||
case "type":
|
||||
// Sort by type first (regular before ec), then by volume ID
|
||||
if allVolumes[i].Type == allVolumes[j].Type {
|
||||
var idI, idJ uint32
|
||||
if allVolumes[i].Type == "regular" {
|
||||
idI = allVolumes[i].RegularVolume.Id
|
||||
} else {
|
||||
idI = allVolumes[i].EcVolume.VolumeID
|
||||
}
|
||||
if allVolumes[j].Type == "regular" {
|
||||
idJ = allVolumes[j].RegularVolume.Id
|
||||
} else {
|
||||
idJ = allVolumes[j].EcVolume.VolumeID
|
||||
}
|
||||
less = idI < idJ
|
||||
} else {
|
||||
less = allVolumes[i].Type < allVolumes[j].Type // "ec" < "regular"
|
||||
}
|
||||
default:
|
||||
// Default to volume ID sort
|
||||
var idI, idJ uint32
|
||||
if allVolumes[i].Type == "regular" {
|
||||
idI = allVolumes[i].RegularVolume.Id
|
||||
} else {
|
||||
idI = allVolumes[i].EcVolume.VolumeID
|
||||
}
|
||||
if allVolumes[j].Type == "regular" {
|
||||
idJ = allVolumes[j].RegularVolume.Id
|
||||
} else {
|
||||
idJ = allVolumes[j].EcVolume.VolumeID
|
||||
}
|
||||
less = idI < idJ
|
||||
}
|
||||
|
||||
if sortOrder == "desc" {
|
||||
return !less
|
||||
}
|
||||
return less
|
||||
})
|
||||
|
||||
// Apply pagination
|
||||
totalVolumesAndEc := len(allVolumes)
|
||||
totalPages := (totalVolumesAndEc + pageSize - 1) / pageSize
|
||||
startIndex := (page - 1) * pageSize
|
||||
endIndex := startIndex + pageSize
|
||||
if endIndex > totalVolumesAndEc {
|
||||
endIndex = totalVolumesAndEc
|
||||
}
|
||||
|
||||
if startIndex >= totalVolumesAndEc {
|
||||
startIndex = 0
|
||||
endIndex = 0
|
||||
}
|
||||
|
||||
// Extract paginated results
|
||||
var paginatedRegularVolumes []VolumeWithTopology
|
||||
var paginatedEcVolumes []EcVolumeWithShards
|
||||
|
||||
for i := startIndex; i < endIndex; i++ {
|
||||
if allVolumes[i].Type == "regular" {
|
||||
paginatedRegularVolumes = append(paginatedRegularVolumes, *allVolumes[i].RegularVolume)
|
||||
} else {
|
||||
paginatedEcVolumes = append(paginatedEcVolumes, *allVolumes[i].EcVolume)
|
||||
}
|
||||
}
|
||||
|
||||
// Convert maps to slices
|
||||
var dcList []string
|
||||
for dc := range dataCenters {
|
||||
dcList = append(dcList, dc)
|
||||
}
|
||||
sort.Strings(dcList)
|
||||
|
||||
var diskTypeList []string
|
||||
for diskType := range diskTypes {
|
||||
diskTypeList = append(diskTypeList, diskType)
|
||||
}
|
||||
sort.Strings(diskTypeList)
|
||||
|
||||
return &CollectionDetailsData{
|
||||
CollectionName: collectionName,
|
||||
RegularVolumes: paginatedRegularVolumes,
|
||||
EcVolumes: paginatedEcVolumes,
|
||||
TotalVolumes: len(regularVolumes),
|
||||
TotalEcVolumes: len(ecVolumes),
|
||||
TotalFiles: totalFiles,
|
||||
TotalSize: totalSize,
|
||||
DataCenters: dcList,
|
||||
DiskTypes: diskTypeList,
|
||||
LastUpdated: time.Now(),
|
||||
Page: page,
|
||||
PageSize: pageSize,
|
||||
TotalPages: totalPages,
|
||||
SortBy: sortBy,
|
||||
SortOrder: sortOrder,
|
||||
}, nil
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user